A System Based on Data Science to Predict Student Dropouts

Scientists from the University of Columbia have used Wi-Fi to determine the number of building occupants. The system relies on occupant count that can vary airflow in a room by consuming less energy.

A System Based on Data Science to Predict Student Dropouts
Image credit: University of Barcelona

Student dropouts extend from early 20th-century pioneers until now, marking trends of causes and prevention. Dropping out of school persists as a problem that interferes with educational system efficiency. According to the estimate from education at a Glance (EAG), almost 30% European students Dropouts College.At the other hand, this rate is in between the 25 percent and 29 percent in Spain. So, to reduce this rate in order to improve academics, scientists have developed a tool based on machine learning techniques for lectures.

The tool gives recommendations for the students and can assess the risk of student dropouts. It proposes a system that relies on objective data to take hidden information which is important for the students’ academic data. And thus, it aids teachers to offer their students a personal and proactive orientation.

Many previous studies on university student dropouts were conducted on the basis of statistical models (data collected via interviews). Statistical models are based on hypotheses taken from the underlying problems. If students’ performance factors change over time, the assumptions of a statistical model could be obsolete.

In this study, researchers used data from the first and second academic years in three bachelor degrees: mathematics, computer science, and law. They primarily applied five data science algorithms with the accuracy of 82%.

The system also shows the grades of students in future courses. It indirectly enables the teachers to give advice or orientation to students based on grades.

Research led Laura Igual said, “However, machine learning techniques have a predictive use based on objective data, which makes them more adaptable to new data. However, statistical systems are better at determining the reasons students leave their studies.”

But the predictive power of these tools is lower. Also, this new focus will allow the teaching staff to have “warnings” about students before registering.”